Hive

• Big idea: Fault containment vs fault tolerance
• Fault tolerance requires extra resources
  • What if you're app uses all machine resources? Can't be fault tolerant!
• Add a new level of abstraction: the cell
  • A Cell is the unit of fault containment
  • Cell crashes should not toast other cells
• If sucessful, SMP no worse than a cluster?
  • But get the pro's of hardware shared memory

Previous slide

Next slide

Back to the index

View Graphic Version

No notes for slide 27